{"id":"https://openalex.org/W3093481237","doi":"https://doi.org/10.48550/arxiv.2010.09141","title":"Diverse Data Selection under Fairness Constraints","display_name":"Diverse Data Selection under Fairness Constraints","publication_year":2020,"publication_date":"2020-10-18","ids":{"openalex":"https://openalex.org/W3093481237","doi":"https://doi.org/10.48550/arxiv.2010.09141","mag":"3093481237"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2010.09141","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.09141","pdf_url":"https://arxiv.org/pdf/2010.09141","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.09141","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004206501","display_name":"Zafeiria Moumoulidou","orcid":"https://orcid.org/0009-0000-1019-3684","observed_orcids":["https://orcid.org/0009-0000-1019-3684"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moumoulidou, Zafeiria","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101979548","display_name":"Andrew McGregor","orcid":"https://orcid.org/0000-0002-2124-160X","observed_orcids":["https://orcid.org/0000-0002-2124-160X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"McGregor, Andrew","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019048013","display_name":"Alexandra Meliou","orcid":"https://orcid.org/0000-0001-7346-6002","observed_orcids":["https://orcid.org/0000-0001-7346-6002"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meliou, Alexandra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.5570999979972839,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.5570999979972839,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10991","display_name":"Game Theory and Voting Systems","score":0.2847000062465668,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.030400000512599945,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/diversity-maximization","display_name":"diversity maximization","score":0.7350000143051147},{"id":"https://openalex.org/keywords/fairness-constraints","display_name":"fairness constraints","score":0.7170000076293945},{"id":"https://openalex.org/keywords/group-fairness","display_name":"group fairness","score":0.36000001430511475},{"id":"https://openalex.org/keywords/approximation-algorithms","display_name":"approximation algorithms","score":0.6259999871253967},{"id":"https://openalex.org/keywords/np-completeness","display_name":"NP-completeness","score":0.9620000123977661},{"id":"https://openalex.org/keywords/metric-spaces","display_name":"metric spaces","score":0.8690000176429749},{"id":"https://openalex.org/keywords/overlapping-groups","display_name":"overlapping groups","score":0.5249999761581421},{"id":"https://openalex.org/keywords/dataset-selection","display_name":"data selection","score":0.574999988079071},{"id":"https://openalex.org/keywords/recommender-systems","display_name":"recommender systems","score":0.34200000762939453}],"concepts":[{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6663706302642822},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5099865198135376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18188351392745972}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2010.09141","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.09141","pdf_url":"https://arxiv.org/pdf/2010.09141","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2010.09141","doi":"https://doi.org/10.48550/arxiv.2010.09141","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.09141","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.09141","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.09141","pdf_url":"https://arxiv.org/pdf/2010.09141","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7307999730110168,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W168294226","https://openalex.org/W1504633543","https://openalex.org/W1965734368","https://openalex.org/W1973264045","https://openalex.org/W1986998000","https://openalex.org/W1990605847","https://openalex.org/W1991657767","https://openalex.org/W1993320088","https://openalex.org/W1996760769","https://openalex.org/W2001554016","https://openalex.org/W2013749500","https://openalex.org/W2038428842","https://openalex.org/W2039797405","https://openalex.org/W2083305840","https://openalex.org/W2100960835","https://openalex.org/W2102747382","https://openalex.org/W2116812802","https://openalex.org/W2152228468","https://openalex.org/W2294345056","https://openalex.org/W2407950728","https://openalex.org/W2544318541","https://openalex.org/W2608807961","https://openalex.org/W2609189435","https://openalex.org/W2666919929","https://openalex.org/W2704480242","https://openalex.org/W2730550703","https://openalex.org/W2785694663","https://openalex.org/W2787705708","https://openalex.org/W2793509414","https://openalex.org/W2798603477","https://openalex.org/W2913165106","https://openalex.org/W2946943427","https://openalex.org/W2963992001","https://openalex.org/W2964288644","https://openalex.org/W2964751853","https://openalex.org/W3005672955","https://openalex.org/W3029962482","https://openalex.org/W3034462058"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829"],"abstract_inverted_index":{"Diversity":[0],"is":[1,96],"an":[2],"important":[3],"principle":[4],"in":[5,21,99,109],"data":[6,22],"selection":[7],"and":[8,12,78,102,122,129],"summarization,":[9],"facility":[10],"location,":[11],"recommendation":[13],"systems.":[14],"Our":[15],"work":[16],"focuses":[17],"on":[18],"maximizing":[19],"diversity":[20],"selection,":[23],"while":[24],"offering":[25],"fairness":[26,42],"guarantees.":[27],"In":[28],"particular,":[29],"we":[30,61,103,125],"offer":[31],"the":[32,37,70,75,132],"first":[33],"study":[34],"that":[35,53,68,93,111],"augments":[36],"Max-Min":[38],"diversification":[39],"objective":[40],"with":[41],"constraints.":[43],"More":[44],"specifically,":[45],"given":[46],"a":[47,65,80],"universe":[48],"$U$":[49],"of":[50,84,120],"$n$":[51],"elements":[52,85],"can":[54,136],"be":[55,137],"partitioned":[56],"into":[57],"$m$":[58,121],"disjoint":[59],"groups,":[60],"aim":[62],"to":[63,131],"retrieve":[64],"$k$-sized":[66],"subset":[67],"maximizes":[69],"pairwise":[71],"minimum":[72],"distance":[73],"within":[74],"set":[76],"(diversity)":[77],"contains":[79],"pre-specified":[81],"$k_i$":[82],"number":[83],"from":[86],"each":[87],"group":[88],"$i$":[89],"(fairness).":[90],"We":[91],"show":[92],"this":[94],"problem":[95],"NP-complete":[97],"even":[98],"metric":[100],"spaces,":[101],"propose":[104],"three":[105],"novel":[106],"algorithms,":[107],"linear":[108],"$n$,":[110],"provide":[112],"strong":[113],"theoretical":[114],"approximation":[115],"guarantees":[116],"for":[117],"different":[118],"values":[119],"$k$.":[123],"Finally,":[124],"extend":[126],"our":[127],"algorithms":[128],"analysis":[130],"case":[133],"where":[134],"groups":[135],"overlapping.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}